Connect AI to the tools you use.

A connection lets your AI see into another app and take action there: read your notes, check your calendar, create a task, draft an email. Think of a connection like a bridge: it lets your AI cross into the app and do work on the other side. Claude calls these connectors. ChatGPT calls them plugins.

This matters because an AI without connections only knows what you paste into the chat. Last week we said to point your AI to your data. Connections are what make that possible.

One more term you will see: custom connectors, sometimes called MCP servers. Anyone can build one, and it allows you to connect niche tools that Claude or ChatGPT do not support out of the box. Nobody has verified the ones you find online though, so be careful with them. I use one I set up myself for Zoho Invoice, my bookkeeping software.

The takeaway: until you connect your AI to your data, it does not have what it needs to help you.

If you have not connected your first app yet, we will do that now. If you have, use this section to check that you set it up safely.

Choose the app you use the most. For most people that is Gmail or your calendar. I personally use Notion, since that is where my tasks and client notes live. In Claude, hit the + button in any chat and open "Manage connectors," or find Connectors under Customize in settings. In ChatGPT, go to Settings, then Plugins.

Pick the app, sign in, approve the access screen, done. Quick note: Claude's Gmail, Calendar, and Drive connectors work on the free plan; ChatGPT needs a paid plan.

Before you rely on it, know what you are allowing:

• Claude gives every connected tool one of three states: "Always allow," "Needs approval," or "Blocked." Find them in Settings, under Customize, then Connectors.
• ChatGPT asks how often it should check with you, per plugin: "Always ask," "Allow read actions," "Allow low-risk actions" (the default), or "Allow all actions." Find them in Settings, under Plugins.
• Make it ask you first. Set anything that can send, delete, or change things to need your approval. As you get more comfortable and confident in it, give it more freedom. Not the other way around.

Also, use your smartest model when connections are involved, especially for work that matters. Better models make fewer mistakes when they have real access. Then put your new connection to work:

Email: "Take a look at my inbox and tell me what actually needs my attention today."

Calendar: "Take a look at my calendar this week and help me reclaim some of my time. What do I not actually need to be doing?"

Files: "Find the latest version of my [document] in Drive and summarize what changed."

Combining them: "Check my email and my calendar for today. Tell me what is on my schedule and which emails need my attention, pull any related files from Drive, and give me the top three things I should do right now."

The more connections you have, the more you can combine in one prompt. That is where this gets interesting: an agent talking to several systems and doing actual work for you. More on that below.

I want to show you the workflow I use to process my meetings, track my action items, schedule the work, and bill my clients. After a client call, I run one saved skill (we covered skills in the prompting guide): I just tell it to process my meeting. Because the skill has taught it what I want, that one prompt is really talking to four or five apps at once.

Not every meeting needs all of this, but when it runs end to end, it looks like this. The agent calls Krisp or Notion for the meeting recording, extracts the tasks, then reads the full transcript to make sure those tasks are accurate. It adds them to Notion, schedules time on my calendar to work on them, and sometimes gets a head start on a few. It then logs the hours to the client's project in Zoho, since I bill for the call and the work, and sometimes drafts the invoice I send for that work. It can even draft an email to the client in Outlook with a summary or an update on the action items.

On a recent 45-minute client call, the workflow created seven tasks, two contact records, and a searchable meeting record, updated three projects, and verified the changes in about 10 minutes of agent work. For a billable call, it also records the duration and tracks that time against the client's retainer. This saves me about 30 to 60 minutes of post-meeting admin per call. At one of those meetings a week, the high end is about four hours and 20 minutes back each month, more than half a workday, or 52 hours a year.

At five or ten of these calls a week, the time really adds up. At the high end, five calls would give me back about 22 hours a month, or 260 hours a year. Ten would be about 43 hours back each month, more than a full workweek, or 520 hours a year. The agent handles the transcript review, copying, linking, time tracking, and record updates while I move on to something else.

Before anything touches the client, like an invoice or an email, I still manually verify and hit send. The point of connections though is that with the right access and the right limits, the agent can do real work across your apps instead of just answering questions.

My rules, in short: the AI can always read. Anything it writes needs my approval. I still hit send myself. The full guide covers the permission screens step by step, plus what happened the one time my agent wrote into the wrong database.